Basic Machine Learning

Question 1

Algorithm

Answer 1

Step-by-step procedure designed to carry out a task.

Question 2

Change detection

Answer 2

Identifying when a significant change has taken place in a process.

Question 3

Classification

Answer 3

The separation of data into two or more categories, or (a point’s
classification) the category a data point is put into.

Question 4

Classifier

Answer 4

A boundary that separates the data into two or more categories. Also
(more generally) an algorithm that performs classification.

Question 5

Cluster

Answer 5

A group of points identified as near/similar to each other.

Question 6

Cluster center

Answer 6

In some clustering algorithms (like 𝑘𝑘-means clustering), the central
point (often the centroid) of a cluster of data points.

Question 7

Clustering

Answer 7

Separation of data points into groups (“clusters”) based on
nearness/similarity to each other. A common form of unsupervised
learning

Question 8

CUSUM

Answer 8

Change detection method that compares observed distribution mean
with a threshold level of change. Short for “cumulative sum”.

Question 9

Deep learning

Answer 9

Neural network-type model with many hidden layers.

Question 10

Dimension

Answer 10

A feature of the data points (for example, height or credit score). (Note that there is also a mathematical definition for this word.)

Question 11

EM algorithm

Answer 11

Expectation-maximization algorithm.

Question 12

Expectation-maximization

algorithm (EM algorithm)

Answer 12

General description of an algorithm with two steps (often iterated), one that finds the function for the expected likelihood of getting the response given current parameters, and one that finds new parameter
values to maximize that probability.

Question 13

Heuristic

Answer 13

Algorithm that is not guaranteed to find the absolute best (optimal) solution.

Question 14

𝑘-means algorithm

Answer 14

Clustering algorithm that defines 𝑘 clusters of data points, each
corresponding to one of 𝑘 cluster centers selected by the algorithm.

Question 15

𝑘-Nearest-Neighbor (KNN)

Answer 15

Classification algorithm that defines a data point’s category as a function of the nearest 𝑘 data points to it.

Question 16

Kernel

Answer 16

A type of function that computes the similarity between two inputs; thanks to what’s (really!) sometimes known as the “kernel trick”, nonlinear classifiers can be found almost as easily as linear ones.

Question 17

Learning

Answer 17

Finding/discovering patterns (or rules) in data, often that can be applied to new data.

Question 18

Machine

Answer 18

Apparatus that can do something; in “machine learning”, it often refers to both an algorithm and the computer it’s run on. (Fun fact: before
computers were developed, the term “computers” referred to people who did calculations quickly in their heads or on paper!)

Question 19

Margin

Answer 19

For a single point, the distance between the point and the classification boundary; for a set of points, the minimum distance between a point in the set and the classification boundary. Also called the separation.

Question 20

Machine learning

Answer 20

Use of computer algorithms to learn and discover patterns or structure in data, without being programmed specifically for them.

Question 21

Misclassified

Answer 21

Put into the wrong category by a classifier.

Question 22

Neural network

Answer 22

A machine learning model that itself is modeled after the workings of neurons in the brain.

Question 23

Supervised learning

Answer 23

Machine learning where the “correct” answer is known for each data point in the training set.

Question 24

Support vector

Answer 24

In SVM models, the closest point to the classifier, among those in a category. (Note that there is a more-technical mathematical definition too.)

Question 25

Support vector machine (SVM)

Answer 25

Classification algorithm that uses a boundary to separate the data into two or more categories (“classes”).

Question 26

SVM

Answer 26

Support vector machine.

Question 27

Unsupervised learning

Answer 27

Machine learning where the “correct” answer is not known for the data points in the training set.

Question 28

Voronoi diagram

Answer 28

Graphical representation of splitting a plane with two or more special points into regions with one special point each, where each region’s points are closer to the region’s special point than to any other special
point.